© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141815
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esor
    -0.30
    å¼ĢæĿ¥
    -0.26
    erty
    -0.26
    ä¸įä»ħä»ħ
    -0.25
    çļĦæĥħå½¢
    -0.24
    åĩºç¤º
    -0.24
     masters
    -0.24
     erosion
    -0.24
    ä¹IJ
    -0.24
     myself
    -0.24
    POSITIVE LOGITS
    =&
    0.26
    @d
    0.25
    _ABC
    0.25
    Relative
    0.24
    æľĢåħ³éĶ®
    0.23
    &_
    0.23
     Chavez
    0.23
     Bhar
    0.23
    bsolute
    0.23
    对æłĩ
    0.23
    Activations Density 28.116%

    No Known Activations

    This feature has no known activations.